The Million Neighborhoods Map is a novel tool designed to honour too position informal settlements across the world. The tool, made past times the University of Chicago’s Mansueto Institute for Urban Innovation, finds communities amongst express access to roads too thence other services. This agency that the map tin locomote used to position urban areas most inward bespeak of roads, power, water, sanitation too other infrastructure.
On the Million Neighborhoods Map urban areas amongst express access to route networks are colored red, spell settlements amongst high access to streets are colored blue. If yous zoom inward on a metropolis on the map yous tin thence chop-chop position those areas which are most probable to locomote informal settlements, areas which cause got sprung upward amongst niggling planning too mayhap niggling essential infrastructure.
The Million Neighborhoods Map doesn't include much information close how the map was made. However reading betwixt the lines of the 'Interactive explainer' on the map I suspect that machine learning has been used to position informal settlements - specially past times identifying areas amongst a high density of buildings which cause got no instantly access to roads or streets. This seems to locomote supported past times the approach suggested inward the newspaper The Fabric of Our Lives, 1 of whose authors is Luis Bettencourt, the initiative Pritzker Director of the Mansueto Institute for Urban Innovation. This newspaper argues that
"We tin cause got whatever metropolis block too diagnose its score of inaccessibility to each edifice from the shipping network using measures from graph theory too topology. On a larger scale, nosotros tin scan an entire metropolis to position blocks inside which or so buildings lack access."This appears to locomote the approach that has been taken to position informal settlements inward the Million Neighborhood Map.
Another event of using machine learning to position informal settlements has been developed past times Dymaxion Labs. Dymaxion Labs' Maps of Potential Slums too Informal Settlements used machine learning to search the satellite imagery of a disclose of South American cities inward social club to position too discover slums too informal settlements. The resulting maps are beingness used to assistance urban planners too local councils position where vital utilities bespeak to locomote directed.
To assistance position informal settlements Dymaxion Labs used the Random Forest machine learning technique. They applied the Random Forest technique to known informal settlements on satellite imagery from South American cities. The Random Forest classifier finds mutual features flora inward areas amongst known informal settlements too absent from areas without informal settlements. It too then uses the classifier on novel satellite imagery to automatically honour informal settlements inward this satellite imagery.
The Machine Learning techniques developed for the Million Neighborhoods Map too past times Dymaxion Labs tin both locomote used past times governments, local authorities too past times non-profit agencies to position informal settlements. These informal settlements saltation upward organically inward urban areas amongst niggling primal planning. They are thence areas which oftentimes lack basic services, such equally water, sanitation too electricity. Once the place of informal settlements has been identified vital infrastructure tin locomote targeted at these areas. The Million Neighborhoods Map suggests that the same machine learning techniques that cause got been used to position the informal settlements tin also locomote used to locomote out the best way to amend access to streets too roads for the people living inward these neighborhoods.
